Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and multiplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     પરંતુ
    0.47
    መሳ
    0.45
    ग्रेड
    0.44
     शतरंज
    0.44
    asList
    0.44
    руя
    0.44
    시오
    0.44
    Control
    0.43
    encryption
    0.43
    orders
    0.43
    POSITIVE LOGITS
    0.50
     multiplied
    0.46
     ×
    0.45
     blessing
    0.45
     Finn
    0.44
     multiplic
    0.43
     had
    0.43
     with
    0.42
     multiply
    0.42
     bears
    0.42
    Act Density 0.004%

    No Known Activations